M2CAI Workflow Challenge: Convolutional Neural Networks with Time Smoothing and Hidden Markov Model for Video Frames Classification

Abstract

Our approach is among the three best to tackle the M2CAI Workflow challenge. The latter consists in recognizing the operation phase for each frames of endoscopic videos. In this technical report, we compare several classification models and temporal smoothing methods. Our submitted solution is a fine tuned Residual Network-200 on 80% of the training set with temporal smoothing using simple temporal averaging of the predictions and a Hidden Markov Model modeling the sequence.

References in corpus (3)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• All you need is a good init
• Tool and Phase recognition using contextual CNN features

Cited by in corpus (5)

• Less is More: Surgical Phase Recognition with Less Annotations through Self-Supervised Pre-training of CNN-LSTM Networks
• Multi-Task Recurrent Convolutional Network with Correlation Loss for Surgical Video Analysis
• Temporal Memory Relation Network for Workflow Recognition from Surgical Video
• Efficient Frame Extraction: A Novel Approach Through Frame Similarity and Surgical Tool Tracking for Video Segmentation
• A Novel Deep ML Architecture by Integrating Visual Simultaneous Localization and Mapping (vSLAM) into Mask R-CNN for Real-time Surgical Video Analysis